© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 6024
    Prev
    Next
    INDEX
    Explanations

    helicopter rotorcraft rotorcraft

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     traveler
    -0.15
     travelers
    -0.14
     subway
    -0.14
    irlines
    -0.13
     airline
    -0.12
     travel
    -0.12
     traveller
    -0.12
    Rail
    -0.12
     hotel
    -0.12
     Rail
    -0.11
    POSITIVE LOGITS
     helicopter
    0.30
     rotor
    0.26
     helicopters
    0.26
     helicopt
    0.21
     hovering
    0.20
     hel
    0.20
    hel
    0.20
    Rotor
    0.20
     Hel
    0.20
     aerial
    0.19
    Activations Density 0.640%

    No Known Activations